成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	朱晟瓴 Chu, Cheng-Ling
論文名稱：	以慣性感測器為基礎之可攜式手部動作辨識及簽名辨識系統之研發 Development of an Inertial-Sensor-Based Portable Hand Movement and Signature Recognition System
指導教授：	王振興 Wang, Jeen-Shing
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2013
畢業學年度：	101
語文別：	英文
論文頁數：	95
中文關鍵詞：	慣性感測器、動態時間扭曲、手部動作辨識、簽名辨識
外文關鍵詞：	inertial sensor, dynamic time warping, hand movement recognition, signature recognition
相關次數：	點閱：118 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本論文旨在開發以慣性感測器為基礎之可攜式數位電子筆及其手部動作及簽名辨識系統。此可攜式數位電子筆包含了三軸加速度計、三軸陀螺儀、三軸磁力計、微控制器及無線射頻傳輸模組。使用者可以在無書寫空間限制的環境下以正常速度進行文字書寫、手勢操控及簽名。在手部動作辨識演算法方面，我們利用零速度補償演算法及基於四元數的非線性互補式濾波器來降低微感測器訊號的雜訊及漂移在速度、軌跡及姿態估測上所造成的誤差；接著透過基於動態時間扭曲(dynamic time warping, DTW)演算法的辨識器成功地辨識二維平面書寫的數字、小寫英文字母、簽名及三維空間的數字及手勢。而在簽名辨識之部分另外有防偽機制演算法，依據辨識器對各樣板訊號及測試訊號透過動態時間扭曲演算法得到的相似程度分數，經由同等錯誤率(Equal Error Rate)制定防偽機制，進而提高簽名辨識系統之鑑別度。此外，本論文亦針對動態時間扭曲及動態極點扭曲辨識器開發最小組內差異暨最大組間差異之樣板挑選演算法(minimal intra-class to maximal inter-class based template selection method, Min-Max template selection method)，以挑選出最佳樣板進而提升辨識結果。最後，經由實驗結果已成功地驗證可攜式手部動作辨識及簽名辨識系統之有效性。

This thesis presents a portable inertial-sensing-based digital pen with a dynamic time warping (DTW)-based recognition algorithm for hand movement and signature recognition. The portable digital pen device is composed of a triaxial accelerometer, a triaxial gyroscope, a triaxial magnetometer, a microcontroller, and an RF wireless transmission module. Users can utilize this digital pen to write numerals or English lowercase letters, make hand gestures, or generate signatures at normal speed without any space limitation. The proposed DTW-based hand movement recognition algorithm consists of the zero velocity compensation (ZVC) method and a quaternion-based nonlinear complementary filter to reduce the integral errors caused by the intrinsic noise/drift of the accelerometer and gyroscope. In addition, the equal error rate (EER) is used to evaluate the performance of the proposed signature recognition schemes. Furthermore, we have developed a minimal intra-class to maximal inter-class based template selection method (Min-Max template selection method) for DTW recognizer to obtain a superior class separation for better recognition. Finally, the experimental results have successfully validated the effectiveness of the proposed inertial-sensor-based portable hand movement and signature recognition system.

CHINESE ABSTRACT i
ABSTRACT ii
ACKNOWLEDGMENTS iii
TABLE OF CONTENTS iv
LIST OF TABLES vii
LIST OF FIGURES ix
Chapter 1 Introduction 1-1
1 Motivation 1-1
2 Literature Survey 1-2
3 Purpose of the Study 1-5
4 Organization of the Thesis 1-6
Chapter 2 Portable Inertial-Sensing-Based Digital Pen 2-1
1 Accelerometer 2-1
2 Gyroscope 2-2
3 Magnetometer 2-4
4 Microcontroller 2-5
5 RF Wireless Transceiver 2-6
6 Portable Inertial-Sensing-Based Digital Pen 2-7
Chapter 3 Hand Movement Trajectory Reconstruction Algorithm 3-1
1 Signal Preprocessing 3-2
1.1 Calibration 3-3
1.2 Moving Average Filter 3-4
2 Motion Detection 3-4
2.1 Segmentation 3-5
2.2 Movement Signal Acquisition 3-6
2.2.1 Orientation Estimation 3-6
2.2.2 Coordination Transformation and Gravity Compensation 3-12
2.2.3 Velocity and Position Estimation 3-13
2.3 Normalization 3-15
3 Summary of the Hand Movement Trajectory Reconstruction Algorithm 3-15
Chapter 4 Time Alignment-Based Recognition Algorithm 4-1
1 Dynamic Time Warping Algorithm 4-1
2 Template Selection for the DTW Recognizer 4-4
3 DTW Recognizer 4-6
4 Summary of the Recognition Algorithm 4-7
Chapter 5 Experimental Results and Discussion 5-1
1 Calibration Experiment 5-2
2 Hand Movement Recognition Experiments 5-12
2.1 2D/3D Handwritten Digit Recognition 5-12
2.1.1 2D Handwritten Digit Recognition 5-13
2.1.2 3D Handwritten Digit Recognition 5-19
2.2 2D Handwritten English Character Recognition 5-21
2.3 3D Gesture Recognition 5-24
2.4 Discussion of the Hand Movement Recognition 5-25
3 Signature Recognition Experiments 5-28
3.1 Equal Error Rate 5-29
3.2 2D Signature Recognition Experiment with Unskilled Forgers 5-30
3.3 2D Signature Recognition Experiment with Skilled Forgers 5-34
3.4 Discussion of the Signature Recognition 5-35
Chapter 6 Conclusions and Future Work 6-1
1 Conclusions 6-1
2 Future Work 6-2
References 7-1
                                    

[1] K. Altun, B. Barshan, and O. Tunҫel, “Comparative study on classifying human activities with miniature inertial and magnetic sensors,” Pattern Recognition, vol. 43, no. 10, pp. 3605-3620, 2010.
[2] A. Akl, C. Feng, and S. Valaee, “A novel accelerometer-based gesture recognition system,” IEEE Trans. Signal Processing, vol. 59, no. 12, pp. 6197-6205, 2011.
[3] W. C. Bang, W. Chang, K. H. Kang, E. S. Choi, A. Potanin, and D. Y. Kim, “Self-contained spatial input device for wearable computers,” in Proc. IEEE Int’l Conf. Wearable Computers, pp. 26-34, 2003.
[4] G. Bailador, C. S. Avila, J. G. Casanova, and A. de S. Sierra, “Analysis of pattern recognition techniques for in-air signature biometrics,” Pattern Recognition, vol. 44, no. 10-11, pp. 2468-2478, 2011.
[5] M. Bashir and F. Kempf, “Advanced biometric pen system for recording and analyzing handwriting,” Journal of Signal Processing Systems, vol. 68, no. 1, pp. 75-81, 2012.
[6] C. M. N. Brigante, N. Abbate, A. Basile, A. C. Faulisi, and S. Sessa, “Towards miniaturization of a MEMS-based wearable motion capture system,” IEEE Trans. Industrial Electronics, vol. 58, no. 8, pp. 3234-3241, 2011.
[7] H. Bunke, J. Csirik, Z. Gingl, and E. Griechisch, “Online signature verification method based on the acceleration signals of handwriting samples,” Lecture Notes in Computer Science, vol. 7042, pp. 499-506, 2011.
[8] M. J. Caruso, “Application of magnetoresistive sensors in navigation systems,” Sens. Actuators, 1997.
[9] Z. Dong, C. Wejinya, and W. J. Li, “An optical-tracking calibration method for MEMS-based digital writing instrument,” IEEE Sensors Journal, vol. 10, no. 10, pp. 1543-1551, 2010.
[10] H. Feng and C. C. Wah, “Online signature verification using a new extreme points warping technique,” Pattern Recognition Letters, vol. 24, no. 16, pp. 2943-2951, 2003.
[11] P. Fang, Z. C. Wu, F. Shen, Y. J. Ge, and B. Fang, “Improved DTW algorithm for online signature verification based on writing forces,” Lecture Notes in Computer Science, vol. 3644, pp. 631-640, 2005.
[12] H. Fourati, N. Manamanni, L. Afilal, and H. Handrich, “A nonlinear filtering approach for the attitude and dynamic body acceleration estimation based on inertial and magnetic sensors: Bio-logging application,” IEEE Sensor Journal, vol. 11 no. 1, pp. 233-243, 2011.
[13] C. Gruber, T. Gruber, S. Krinninger, and B. Sick, “Online signature verification with support vector machines based on LCSS kernel functions,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 40, no. 4, pp. 1088-1100, 2010.
[14] A. K. Jain, A. Ross, and S. Prabhakar, “An introduction to biometric recognition,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 4-20, 2004.
[15] Y. S. Kim, B. S. Soh, and S. G. Lee, “A new wearable input device: SCURRY,” IEEE Trans. Industrial Electronics, vol. 52, pp. 1490-1499, 2005.
[16] S. Kallio, J. Kela, P. Korpipӓӓ, and J. Mӓntyjӓrvi, “User independent gesture interaction for small handheld devices,” Int. J. Patt. Recogn. Artif. Intell., vol. 20, no. 4, pp. 505-524, 2006.
[17] S. Katsura and K. Ohishi, “Acquisition and analysis of finger motions by skill preservation system” IEEE Trans. Industrial Electronics, vol. 54, pp. 3353-3361, 2007.
[18] S. Kim, G. Park, S. Yim, S. Choi, and S. Choi, “Gesture-recognizing hand-held interface with vibrotactile feedback for 3D interaction,” IEEE Trans. Consumer Electronics, vol. 55, no. 3, pp. 1169-1177, 2009.
[19] M. H. Ko, G. West, S. Venkatesh, and M. Kumar, “Using dynamic time warping for online temporal fusion in multisensor systems,” Information Fusion, vol. 9, no. 3, pp. 370-388, 2010.
[20] J. Liu, L. Zhong, J. Wickramasuriya, and V. Vasudevan, “uWave: Accelerometer-based personalized gesture recognition and its applications,” Pervasive and Mobile Computing, vol. 5, no. 6, pp. 657-675, 2009.
[21] S. Mitra and T. Acharya, “Gesture recognition: A survey,” IEEE Trans. Systems Man and Cybernetics, vol. 37, no. 3, pp. 311-324, 2007.
[22] R. Muscillo, M. Schmid, S. Conforto, and T. D’Alessio, “Early recognition of upper limb motor tasks through accelerometers: Real-time implementation of a DTW-based algorithm,” Computers in Biology and Medicine, vol. 41, no. 3, pp. 164-172, 2011.
[23] K. A. Toh, J. Kim, and S. Lee, “Biometric scores fusion based on total error rate minimization,” Pattern Recognition, vol. 41, no. 3, pp. 1066-1082, 2008.
[24] C. Verplaetse, “Inertial proprioceptive devices: Self-motion-sensing toys and tools,” IBM Systems Journal, vol. 35, no. 3-4, pp. 639-650, 1996.
[25] S. Wu and Y. F. Li, “Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition,” Pattern Recognition, vol. 42, no. 1, pp. 194-214, 2009.
[26] J. S. Wang, Y. L. Hsu, and J. N. Liu, “An inertial-measurement-unit-based pen with a trajectory reconstruction algorithm and its applications,” IEEE Trans. Industrial Electronics, vol. 57, no. 10, pp. 3508-3521, 2010.
[27] J. S. Wang and F. C. Chuang, “An accelerometer-based digital pen with a trajectory recognition algorithm for handwritten digit and gesture recognition,” IEEE Trans. Industrial Electronics, vol. 59, no. 7, pp. 2998-3007, 2012.
[28] R. Xu, S. Zhou, and W. J. Li, “MEMS accelerometer based nonspecific-user hand gesture recognition,” IEEE Sensors Journal, vol. 12, no. 5, pp. 1166-1173, 2012.
[29] M. F. Zanuy, “On-line signature recognition based on VQ-DTW,” Pattern Recognition, vol. 40, no. 3, pp. 981-992, 2007.

校內：2023-12-31公開
校外：2023-12-31公開

簡易檢索 / 詳目顯示

相關論文